# Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning

arXiv: https://arxiv.org/abs/2508.06218 · HTML: https://mlsanity.com/paper/2508.06218/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Deep Learning for Rheumatoid Arthritis: Joint Detection and Damage Scoring in X-rays](https://mlsanity.com/paper/2104.13915/) (2021)
- [Rheumatoid Arthritis: Automated Scoring of Radiographic Joint Damage](https://mlsanity.com/paper/2110.08812/) (2021)
- [Deep Learning Models to Automate the Scoring of Hand Radiographs for Rheumatoid Arthritis](https://mlsanity.com/paper/2406.09980/) (2024)

## Built on by (most cited first, 1 of 1)

- [Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases](https://mlsanity.com/paper/2603.21935/) (2026)

## Abstract (arXiv)

The Sharp/van der Heijde (SvdH) score has been widely used in clinical trials to quantify radiographic damage in Rheumatoid Arthritis (RA), but its complexity has limited its adoption in routine clinical practice. To address the inefficiency of manual scoring, this work proposes a two-stage pipeline for interpretable image-level SvdH score prediction using dual-hand radiographs. Our approach extracts disease-relevant image regions and integrates them using attention-based multiple instance learning to generate image-level features for prediction. We propose two region extraction schemes: 1) sampling image tiles most likely to contain abnormalities, and 2) cropping patches containing disease-relevant joints. With Scheme 2, our best individual score prediction model achieved a Pearson's correlation coefficient (PCC) of 0.943 and a root mean squared error (RMSE) of 15.73. Ensemble learning further boosted prediction accuracy, yielding a PCC of 0.945 and RMSE of 15.57, achieving state-of-the-art performance that is comparable to that of experienced radiologists (PCC = 0.97, RMSE = 18.75). Finally, our pipeline effectively identified and made decisions based on anatomical structures which clinicians consider relevant to RA progression.